Downloads · 30 days
110
11% of all-time downloads
RichardErkhov/DopeorNope_-_SOLARC-MOE-10.7Bx4-gguf
DopeorNope_-_SOLARC-MOE-10.7Bx4-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
110
11% of all-time downloads
All-time downloads
968
Public
Repo size
407 GB
Likes
0
Public
Click a slice to open those files.
.gguf471 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
SOLARC-MOE-10.7Bx4 - GGUF
| Name | Quant method | Size |
|---|---|---|
| SOLARC-MOE-10.7Bx4.Q2_K.gguf | Q2_K | 12.28GB |
| SOLARC-MOE-10.7Bx4.IQ3_XS.gguf | IQ3_XS | 13.74GB |
| SOLARC-MOE-10.7Bx4.IQ3_S.gguf | IQ3_S | 14.52GB |
| SOLARC-MOE-10.7Bx4.Q3_K_S.gguf | Q3_K_S | 14.5GB |
| SOLARC-MOE-10.7Bx4.IQ3_M.gguf | IQ3_M | 14.8GB |
| SOLARC-MOE-10.7Bx4.Q3_K.gguf | Q3_K | 16.1GB |
| SOLARC-MOE-10.7Bx4.Q3_K_M.gguf | Q3_K_M | 16.1GB |
| SOLARC-MOE-10.7Bx4.Q3_K_L.gguf | Q3_K_L | 17.45GB |
| SOLARC-MOE-10.7Bx4.IQ4_XS.gguf | IQ4_XS | 18.13GB |
| SOLARC-MOE-10.7Bx4.Q4_0.gguf | Q4_0 | 18.95GB |
| SOLARC-MOE-10.7Bx4.IQ4_NL.gguf | IQ4_NL | 19.13GB |
| SOLARC-MOE-10.7Bx4.Q4_K_S.gguf | Q4_K_S | 19.11GB |
| SOLARC-MOE-10.7Bx4.Q4_K.gguf | Q4_K | 20.33GB |
| SOLARC-MOE-10.7Bx4.Q4_K_M.gguf | Q4_K_M | 20.33GB |
| SOLARC-MOE-10.7Bx4.Q4_1.gguf | Q4_1 | 21.04GB |
| SOLARC-MOE-10.7Bx4.Q5_0.gguf | Q5_0 | 23.13GB |
| SOLARC-MOE-10.7Bx4.Q5_K_S.gguf | Q5_K_S | 23.13GB |
| SOLARC-MOE-10.7Bx4.Q5_K.gguf | Q5_K | 23.84GB |
| SOLARC-MOE-10.7Bx4.Q5_K_M.gguf | Q5_K_M | 23.84GB |
| SOLARC-MOE-10.7Bx4.Q5_1.gguf | Q5_1 | 25.23GB |
| SOLARC-MOE-10.7Bx4.Q6_K.gguf | Q6_K | 27.58GB |
| SOLARC-MOE-10.7Bx4.Q8_0.gguf | Q8_0 | 35.73GB |
language:
The license is cc-by-nc-sa-4.0.
Model Developers Seungyoo Lee(DopeorNope)
I am in charge of Large Language Models (LLMs) at Markr AI team in South Korea.
Input Models input text only.
Output Models generate text only.
Model Architecture
SOLARC-MOE-10.7Bx4 is an auto-regressive language model based on the SOLAR architecture.
kyujinpy/Sakura-SOLAR-Instruct
Weyaxi/SauerkrautLM-UNA-SOLAR-Instruct
VAGOsolutions/SauerkrautLM-SOLAR-Instruct
fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
I have built a model using the Mixture of Experts (MOE) approach, utilizing each of these models as the base.
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
repo = "DopeorNope/SOLARC-MOE-10.7Bx4"
OpenOrca = AutoModelForCausalLM.from_pretrained(
repo,
return_dict=True,
torch_dtype=torch.float16,
device_map='auto'
)
OpenOrca_tokenizer = AutoTokenizer.from_pretrained(repo)